security MCP Server
Android Pentest AI Assistant (APAIA) is an MCP server for Claude Desktop that was specifically created for Android pentesting/bug bounty purposes and aims to provide assistance for recon, static code analysis and exploits using ADB and JADX.
Discovered via github-topic:mcp-server and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
View decoded AndroidManifest.xml
Providers with authorities, permissions, grantUriPermissions
uiautomator XML dump (find coordinates)
Pull file from device
Exported activities/services/receivers/providers — parsed from real manifest
ENTER=66, DEL=67, BACK=4, TAB=61
Description
Browse decompiled files (filter by path/extension)
password', context_lines=5) jadx_search('com.example.app', pattern='setJavaScriptEnabled') jadx_search('com.example.app', pattern='MODE_WORLD_READABLE') jadx_search('com.example.app', pattern='SELECT.*FROM', file_filter='*.java') jadx_list_files('com.example.app', extension='java', path_filter='sources/com/example/auth') jadx_read_file('com.example.app', 'sources/com/example/LoginActivity.java') # 5. Interact with components open_deeplink('myapp://reset?token=INJECT') send_intent(action='com.example.ADMIN_ACTION', component='com.example/.AdminActivity') poc_query_content_provider(uri='content://com.example.provider/users') # 6. UI PoC take_screenshot() # → find element positions dump_ui_hierarchy() # → get exact coordinates poc_bruteforce_login( username='[email protected]', passwords=['admin','password','1234','test123'], username_coords=[540,800], password_coords=[540,960], submit_coords=[540,1100], success_indicator='Dashboard' ) # 7. Runtime analysis capture_logcat(package='com.example.app', duration_seconds=10, level='D') list_app_files('com.example.app', path='/shared_prefs') pull_app_file(package='com.example.app', remote_path='/data/data/com.example.app/shared_prefs/prefs.xml', local_path='/tmp/prefs.xml') ``` --- ## Environment Variables
Decompile: `manifest_only` (5s, recon) or `full` (30–300s, source)
Declared + runtime-granted permissions
Screen capture to local PNG
Browse app data dir (run-as / root)
Version, SDK, paths, debuggable
Type into focused field
Unauth access + SQLi testing
Pull APK(s) from device. Handles split APKs.
URI schemes + intent filter data from manifest
Select-all + delete
Timed logcat (filter by tag/package)
Filter: all/system/third-party
Show what's been pulled/decompiled
Batch intent sending with varying extras
`~/.android-pentest`
OS, arch, SELinux, root
Grep across all Java sources (secrets, URLs, crypto…)
Open a URI on device
Deep link fuzzer with `{FUZZ}` template
`jadx` (from PATH)
Connected ADB devices
Read a specific Java/XML file
am start/broadcast/startservice with typed extras
UI bruteforce with success/failure detection
Description
真实性验证技能。分析用户提供的信息、消息、图片或内容，判断其真实性和可信度，识别虚假信息、AI生成内容或伪造内容。
Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators
Pod Security Standards (PSS) define three levels of security policies -- Privileged, Baseline, and Restricted -- enforced by the Pod Security Admission (PSA) controller built into Kubernetes 1.25+. PS
Implements eBPF-based security monitoring using Cilium Tetragon for real-time process execution tracking, network connection observability, file access auditing, and runtime enforcement. Covers TracingPolicy CRD authoring with kprobe/tracepoint hooks, in-kernel filtering via matchArgs/matchBinaries selectors, JSON event export, and integration with SIEM pipelines. Use when building kernel-level runtime security observability for Linux hosts or Kubernetes clusters.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Learn how to use the absolute-audit Claude skill. Complete guide with installation instructions and examples.
Learn how to use the token-scam-analysis Claude skill. Complete guide with installation instructions and examples.
Learn how to use the absolute-upgrade Claude skill. Complete guide with installation instructions and examples.